File size: 3,147 Bytes
801a24b |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 |
import streamlit as st
import cv2
import torch
from PIL import Image
from transformers import AutoImageProcessor, AutoModelForImageClassification
from io import BytesIO
import numpy as np
# Load processor and model
processor = AutoImageProcessor.from_pretrained("RickyIG/emotion_face_image_classification")
model = AutoModelForImageClassification.from_pretrained("RickyIG/emotion_face_image_classification")
# Title of the Streamlit app
st.title("Emotion Detection App")
# Option to choose between uploading image or using live camera
option = st.radio("Select an option", ("Upload Image", "Use Live Camera"))
if option == "Upload Image":
# Upload image
uploaded_file = st.file_uploader("Choose an image...", type=["jpg", "jpeg", "png"])
if uploaded_file is not None:
# Display the uploaded image
image = Image.open(uploaded_file)
st.image(image, caption="Uploaded Image", use_column_width=True)
# Preprocess the image
inputs = processor(images=image, return_tensors="pt")
# Make predictions
with torch.no_grad():
outputs = model(**inputs)
logits = outputs.logits # raw model outputs (before softmax)
predicted_class_idx = logits.argmax(-1).item() # predicted class index
# Get the label of the predicted class
label = model.config.id2label[predicted_class_idx]
# Display the result
st.write(f"Predicted Emotion: {label}")
elif option == "Use Live Camera":
# Use OpenCV to capture video from the front camera
cap = cv2.VideoCapture(0)
if not cap.isOpened():
st.error("Error: Could not open webcam.")
else:
stframe = st.empty() # Placeholder to display live camera feed
while True:
# Capture frame-by-frame
ret, frame = cap.read()
if not ret:
st.error("Error: Failed to capture frame.")
break
# Convert frame (BGR) to RGB (PIL format)
image = Image.fromarray(cv2.cvtColor(frame, cv2.COLOR_BGR2RGB))
# Preprocess the image
inputs = processor(images=image, return_tensors="pt")
# Make predictions
with torch.no_grad():
outputs = model(**inputs)
logits = outputs.logits # raw model outputs (before softmax)
predicted_class_idx = logits.argmax(-1).item() # predicted class index
# Get the label of the predicted class
label = model.config.id2label[predicted_class_idx]
# Display the result
cv2.putText(frame, f"Emotion: {label}", (10, 30), cv2.FONT_HERSHEY_SIMPLEX, 1, (0, 255, 0), 2, cv2.LINE_AA)
# Convert the frame to RGB for Streamlit
frame_rgb = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
stframe.image(frame_rgb, channels="RGB", use_column_width=True)
# Release the capture when finished
cap.release()
|